{"total":18,"rows":[{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2502.17810","title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","created":"2025-02-25","cited_by_count":30,"area":null},{"id":"2505.19037","title":"Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models","created":"2025-05-25","cited_by_count":27,"area":null},{"id":"2509.26388","title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","created":"2025-09-30","cited_by_count":13,"area":null},{"id":"2503.02769","title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training","created":"2025-03-04","cited_by_count":11,"area":null},{"id":"2507.22968","title":"C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations","created":"2025-07-30","cited_by_count":9,"area":null},{"id":"2511.00850","title":"MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models","created":"2025-11-02","cited_by_count":9,"area":null},{"id":"2507.18061","title":"TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2608.19515","title":"Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2509.26329","title":"TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2602.02557","title":"The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.07599","title":"StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2603.09881","title":"Do What I Say: A Spoken Prompt Dataset for Instruction-Following","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.18678","title":"Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2608.09189","title":"EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.23416","title":"MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier Auditing","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2604.19782","title":"KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness","created":"2026-03-30","cited_by_count":0,"area":null}],"next_cursor":null}